Model comparison
Mixtral 8x22B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Yi-Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 15.1.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Mixtral 8x22B | Yi-Lightning | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 27.1 | 37.1 |
| Released | 2024-04-17 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 64K | — |
| Max output | 64K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-Lightning leads
Mixtral 8x22B: 24.2 (#329), Yi-Lightning: 27.4 (#320)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1166 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |
Agentic & Tool Use Not comparable
Mixtral 8x22B: 23.1 (#127), Yi-Lightning: —
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| Cybench | 7.5% | — |
Reasoning Yi-Lightning leads
Mixtral 8x22B: 19.9 (#248), Yi-Lightning: 25.9 (#139)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1302 |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |
Math Yi-Lightning leads
Mixtral 8x22B: 22.9 (#275), Yi-Lightning: 36.2 (#172)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1184 | 1300 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |
Knowledge Yi-Lightning leads
Mixtral 8x22B: 15.1 (#293), Yi-Lightning: 35.4 (#185)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1113 | 1286 |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |
Multilingual Yi-Lightning leads
Mixtral 8x22B: 32.8 (#255), Yi-Lightning: 42.2 (#196)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1128 | 1269 |
| LMArena Chinese | 1116 | 1320 |
| LMArena French | 1166 | 1305 |
| LMArena German | 1141 | 1267 |
| LMArena Japanese | 1037 | 1228 |
| LMArena Korean | 1057 | 1192 |
| LMArena Russian | 1158 | 1255 |
| LMArena Spanish | 1151 | 1315 |
Instruction Following Yi-Lightning leads
Mixtral 8x22B: 57.7 (#266), Yi-Lightning: 67.4 (#196)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1147 | 1278 |
| IFEval | 72.4% | — |
Long Context Yi-Lightning leads
Mixtral 8x22B: 34.7 (#247), Yi-Lightning: 39.4 (#181)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1144 | 1297 |
Writing & Preference Yi-Lightning leads
Mixtral 8x22B: 36.9 (#262), Yi-Lightning: 50.2 (#184)
| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1162 | 1302 |
| LMArena Creative Writing | 1141 | 1280 |
| LMArena Multi-Turn | 1130 | 1311 |
| WildBench | 71.1% | — |
Frequently asked questions
Is Mixtral 8x22B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.
Is Mixtral 8x22B or Yi-Lightning better for coding?
Yi-Lightning scores higher on coding benchmarks: 27.4 versus 24.2 in the Noometry coding category.
How many benchmarks do Mixtral 8x22B and Yi-Lightning share?
17 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Yi-Lightning has 18.